Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15249
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships in coding or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     she
    -0.56
    QUADS
    -0.53
     yes
    -0.51
     neutron
    -0.48
     Yes
    -0.48
    she
    -0.48
    )$\\
    -0.48
    dotte
    -0.47
    !).
    -0.47
     She
    -0.47
    POSITIVE LOGITS
    eseorang
    0.66
     XCTest
    0.66
     GoogleFonts
    0.65
    dafx
    0.65
     getopt
    0.64
    haikusbot
    0.64
     betweenstory
    0.63
     Baillargeon
    0.62
    AddTagHelper
    0.62
     beginnetje
    0.61
    Activations Density 0.892%

    No Known Activations